AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Decoupled Attention Network for Text Recognition

Tianwei Wang, Yuanzhi Zhu, Lianwen Jin, Canjie Luo, Xiaoxue Chen, Yaqiang Wu, Qianying Wang, Mingxiang Cai

AAAI 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 318 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace recurrent attention alignment with visual-feature-only CAM and a decoupled decoderText recognition with the DAN feature encoder · IAMCER: 9.9 -> 6.4Improved
Replace recurrent attention alignment with visual-feature-only CAM and a decoupled decoderText recognition with the DAN feature encoder · RIMESWER: 9.1 -> 8.9Improved
Use visual-feature-only alignment instead of recurrent attention alignmentDAN on handwritten text · IAMCER: The paper reports a 1.5% CER improvement over previous state-of-the-art.Improved
Set CAM output length to 200 instead of 150 (ablation)DAN · IAMCER: 6.4 -> 6.3No clear effect
Set CAM output length to 250 instead of 150 (ablation)DAN · IAMCER: 6.4 -> 6.4No clear effect
Reduce CAM depth L (ablation)DAN · IAMRecognition performanceHurt
Use 2D rather than 1D DANDAN · IIIT5Kaccuracy: 93.3 -> 94.3Improved
Use 2D rather than 1D DANDAN · IC03accuracy: 95.2 -> 95.0Hurt
Use 2D rather than 1D DANDAN · IC13accuracy: 94.2 -> 93.9Hurt
Use 2D rather than 1D DANDAN · SVT-Paccuracy: 76.8 -> 80.0Improved
Use 2D rather than 1D DANDAN · CUTE80accuracy: 80.6 -> 84.4Improved
Use 2D rather than 1D DANDAN · IC15accuracy: 71.8 -> 74.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy